了解多处理:Python 中的共享内存管理、锁和队列

For those who simply want to copy and paste everything to execute the code, here is the full script:

__author__ = 'Me and myself'

import multiprocessing as mp
import time

def the_job(args):
    """The job for multiprocessing.

    Prints some stuff secured by a lock and 
    finally puts the input into a queue.

    """
    idx = args[0]
    lock = args[1]
    queue=args[2]

    lock.acquire()
    print 'I'
    print 'was '
    print 'here '
    print '!!!!'
    print '1111'
    print 'einhundertelfzigelf
'
    who= ' By run %d 
' % idx
    print who
    lock.release()

    queue.put(idx)


def read_queue(queue):
    """Turns a qeue into a normal python list."""
    results = []
    while not queue.empty():
        result = queue.get()
        results.append(result)
    return results


def make_iterator(args, lock, queue):
    """Makes an iterator over args and passes the lock an queue to each element."""
    return ((arg, lock, queue) for arg in args)


def start_scenario(scenario_number = 1):
    """Starts one of four multiprocessing scenarios.

    :param scenario_number: Index of scenario, 1 to 4

    """
    args = range(10)
    ncores = 3
    if scenario_number==1:
        result =  scenario_1_pool_no_manager(the_job, args, ncores)

    elif scenario_number==2:
        result =  scenario_2_pool_manager(the_job, args, ncores)

    elif scenario_number==3:
        result =  scenario_3_single_processes_no_manager(the_job, args, ncores)

    elif scenario_number==4:
        result =  scenario_4_single_processes_manager(the_job, args, ncores)

    if result != args:
        print 'Scenario %d fails: %s != %s' % (scenario_number, args, result)
    else:
        print 'Scenario %d successful!' % scenario_number


def scenario_1_pool_no_manager(jobfunc, args, ncores):
    """Runs a pool of processes WITHOUT a Manager for the lock and queue.

    FAILS!

    """
    mypool = mp.Pool(ncores)
    lock = mp.Lock()
    queue = mp.Queue()

    iterator = make_iterator(args, lock, queue)

    mypool.map(jobfunc, iterator)

    mypool.close()
    mypool.join()

    return read_queue(queue)


def scenario_2_pool_manager(jobfunc, args, ncores):
    """Runs a pool of processes WITH a Manager for the lock and queue.

    SUCCESSFUL!

    """
    mypool = mp.Pool(ncores)
    lock = mp.Manager().Lock()
    queue = mp.Manager().Queue()

    iterator = make_iterator(args, lock, queue)
    mypool.map(jobfunc, iterator)
    mypool.close()
    mypool.join()

    return read_queue(queue)


def scenario_3_single_processes_no_manager(jobfunc, args, ncores):
    """Runs an individual process for every task WITHOUT a Manager,

    SUCCESSFUL!

    """
    lock = mp.Lock()
    queue = mp.Queue()

    iterator = make_iterator(args, lock, queue)

    do_job_single_processes(jobfunc, iterator, ncores)

    return read_queue(queue)


def scenario_4_single_processes_manager(jobfunc, args, ncores):
    """Runs an individual process for every task WITH a Manager,

    SUCCESSFUL!

    """
    lock = mp.Manager().Lock()
    queue = mp.Manager().Queue()

    iterator = make_iterator(args, lock, queue)

    do_job_single_processes(jobfunc, iterator, ncores)

    return read_queue(queue)


def do_job_single_processes(jobfunc, iterator, ncores):
    """Runs a job function by starting individual processes for every task.

    At most `ncores` processes operate at the same time

    :param jobfunc: Job to do

    :param iterator:

        Iterator over different parameter settings,
        contains a lock and a queue

    :param ncores:

        Number of processes operating at the same time

    """
    keep_running=True
    process_dict = {} # Dict containing all subprocees

    while len(process_dict)>0 or keep_running:

        terminated_procs_pids = []
        # First check if some processes did finish their job
        for pid, proc in process_dict.iteritems():

            # Remember the terminated processes
            if not proc.is_alive():
                terminated_procs_pids.append(pid)

        # And delete these from the process dict
        for terminated_proc in terminated_procs_pids:
            process_dict.pop(terminated_proc)

        # If we have less active processes than ncores and there is still
        # a job to do, add another process
        if len(process_dict) < ncores and keep_running:
            try:
                task = iterator.next()
                proc = mp.Process(target=jobfunc,
                                                   args=(task,))
                proc.start()
                process_dict[proc.pid]=proc
            except StopIteration:
                # All tasks have been started
                keep_running=False

        time.sleep(0.1)


def main():
    """Runs 1 out of 4 different multiprocessing scenarios"""
    start_scenario(1)


if __name__ == '__main__':
    main()

解决方案

multiprocessing.Lock 是使用操作系统提供的 Semaphore 对象实现的.在 Linux 上，子进程只是通过 os.fork 从父进程继承信号量的句柄.这不是信号量的副本；它实际上继承了父级具有的相同句柄，可以继承文件描述符的相同方式.另一方面，Windows 不支持 os.fork，因此它必须腌制 Lock.它通过使用 Windows DuplicateHandle API，其中指出:

class SemLock(object):

    def __init__(self, kind, value, maxvalue):
        sl = self._semlock = _multiprocessing.SemLock(kind, value, maxvalue)
        debug('created semlock with handle %s' % sl.handle)
        self._make_methods()

        if sys.platform != 'win32':
            def _after_fork(obj):
                obj._semlock._after_fork()
            register_after_fork(self, _after_fork)

    def _make_methods(self):
        self.acquire = self._semlock.acquire
        self.release = self._semlock.release
        self.__enter__ = self._semlock.__enter__
        self.__exit__ = self._semlock.__exit__

    def __getstate__(self):  # This is called when you try to pickle the `Lock`.
        assert_spawning(self)
        sl = self._semlock
        return (Popen.duplicate_for_child(sl.handle), sl.kind, sl.maxvalue)

    def __setstate__(self, state): # This is called when unpickling a `Lock`
        self._semlock = _multiprocessing.SemLock._rebuild(*state)
        debug('recreated blocker with handle %r' % state[0])
        self._make_methods()

#
# Check that the current thread is spawning a child process
#

def assert_spawning(self):
    if not Popen.thread_is_spawning():
        raise RuntimeError(
            '%s objects should only be shared between processes'
            ' through inheritance' % type(self).__name__
            )

@staticmethod
def thread_is_spawning():
    return False

def dump(obj, file, protocol=None):
    ForkingPickler(file, protocol).dump(obj)

class Popen(object):
    '''
    Start a subprocess to run the code of a process object
    '''
    _tls = thread._local()

    def __init__(self, process_obj):
        ...
        # send information to child
        prep_data = get_preparation_data(process_obj._name)
        to_child = os.fdopen(wfd, 'wb')
        Popen._tls.process_handle = int(hp)
        try:
            dump(prep_data, to_child, HIGHEST_PROTOCOL)
            dump(process_obj, to_child, HIGHEST_PROTOCOL)
        finally:
            del Popen._tls.process_handle
            to_child.close()


    @staticmethod
    def thread_is_spawning():
        return getattr(Popen._tls, 'process_handle', None) is not None

lock = None
def initialize_lock(l):
   global lock
   lock = l

def scenario_1_pool_no_manager(jobfunc, args, ncores):
    """Runs a pool of processes WITHOUT a Manager for the lock and queue.

    """
    lock = mp.Lock()
    mypool = mp.Pool(ncores, initializer=initialize_lock, initargs=(lock,))
    queue = mp.Queue()

    iterator = make_iterator(args, queue)

    mypool.imap(jobfunc, iterator) # Don't pass lock. It has to be used as a global in the child. (This means `jobfunc` would need to be re-written slightly.

    mypool.close()
    mypool.join()

return read_queue(queue)